finish
4 registry entries were observed exposing a tool named finish — none of them flagged as a privileged capability.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 13,559 of 46,301 scannable entries (29%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- v3.7.0↓ 4k/wk★ 1k
Verify a running web app from the inside over MCP: look, act, observe, assert. No screenshots.
ClaudeCursorCopilotGeminimcp - v0.18.0↓ 2k/wk★ 1
Open-source AI agent that QA-tests your website's analytics, ad and consent tracking (GA4, GTM, Google Ads, Meta, TikTok). Bring your own model (Claude, OpenAI, Gemini) or use it from your chat app over MCP.
ClaudeCursorCopilotGeminianalyticsga4google-tag-managertrackingqaconsent-mode - v2026.1014.1↓ 1k/wk★ 5
Vibgrate CLI scans your manifests — never your source — and scores drift (DriftScore) and exposure (RiskScore) separately. Free, offline, in about a minute.
ClaudeCursorCopilotGeminicode-graphcodebase-intelligenceasttree-sittermcpai-agents - v0.21.0↓ 47/wk★ 4
End-to-end tests without test code. Write one sentence, an agent drives a real browser and returns a verdict, and a passing run is recorded so the next one calls no model. Runs on any URL with no account.
ClaudeCursorCopilotGeminie2e-testingend-to-end-testingtestingtest-automationplaywrightqa